© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6222
    Prev
    Next
    INDEX
    Explanations

    Earthquakes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     financiamento
    -0.09
     préstamos
    -0.09
     борь
    -0.08
    battle
    -0.08
     conflictos
    -0.08
    гр
    -0.08
     plague
    -0.08
     holdem
    -0.08
     люблю
    -0.08
    люб
    -0.08
    POSITIVE LOGITS
     magnitude
    0.09
     chil
    0.08
    agnitude
    0.07
    Magnitude
    0.07
    급
    0.07
    ANI
    0.07
    Worth
    0.07
     Masa
    0.07
     বিব
    0.07
     di
    0.07
    Activations Density 0.001%

    No Known Activations